© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49710
    Prev
    Next
    INDEX
    Explanations

    accessible and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atan
    -0.08
    aison
    -0.08
    utow
    -0.07
    avais
    -0.07
    enate
    -0.07
    ertes
    -0.07
    รà¹īาย
    -0.07
    athers
    -0.07
    athan
    -0.07
    åľ¨æĸ½å·¥
    -0.07
    POSITIVE LOGITS
    -minded
    0.11
     minded
    0.09
     banget
    0.09
    ä½Ĩä¸įéĻIJäºİ
    0.08
    èIJ½æĪ·
    0.08
    æĺĵæĩĤ
    0.07
    ness
    0.07
    нее
    0.07
    ä¸Ģæĸij
    0.07
    ãĤĦãģĭãģ«
    0.07
    Activations Density 0.009%

    No Known Activations